The Industry 4.0 revolution is changing the manufacturing landscape. A broad set of new technologies emerged (including software and connected equipment) that digitise manufacturing systems. These technologies bring new vitality and opportunities to the manufacturing industry, but they also bring new challenges. This paper focuses on the impact of Industry 4.0 on production planning approaches and software. We first propose a digital twin framework that integrates production planning systems and frontier technologies. The frontier technologies that may impact production planning software are the internet of things, cloud manufacturing, blockchain, and big data analytics. Second, we provide a state-of-the-art on the application of each technology in the production planning, as well as a detailed analysis of the benefit and application status. Finally, this paper discusses the future research and application directions in the production planning. We conclude that Industry 4.0 will lead to the construction of data-driven models for production planning software. These tools will include models built accurately from data, account for uncertainty, and partially actuate the decision autonomously.

In recent years, the literature has paid considerable attention to digital twin technology for the implementation of Industry 4.0 and intelligent manufacturing. Most of the literature argues that simulation models are a key platform for digital twins and considers discrete-event simulation to be a suitable method to model real dynamic manufacturing systems. However, the discrete-event simulation of complex manufacturing systems is a time-consuming process. Therefore, it is difficult to deal with the large-scale discrete optimisation problems in digital twin shop floors. To bridge this research gap, we propose an improved multi-fidelity simulation-based optimisation method based on multi-fidelity optimisation with ordinal transformation and optimal sampling (MO2TOS) in the current research. The proposed method embeds heuristic algorithms to accelerate the solution space search efficiency in MO2TOS. Moreover, we develop an improved multi-fidelity simulation-based optimisation system by integrating the proposed method with discrete-event simulation tools and apply this system to a digital twin-based aircraft parts production workshop. Based on this digital twin shop floor, we conduct different production planning experiments to evaluate the performance of the proposed method. The experimental results demonstrate that the proposed improved multi-fidelity simulation-based optimisation method is well-applied in solving large-scale problems and outperforms other simulation-based optimisation methods.

In recent years, more manufacturing enterprises are building automated flexible production lines (AFPLs) to satisfy the dynamic and diversified demand. Currently, static planning methods can hardly meet the requirements of the dynamic resource allocation for AFPLs. The technologies of the digital twin can help solve dynamic problems. Therefore, we propose a data-driven cloud simulation architecture for AFPLs in smart factories. First, we design a cloud simulation platform as the architecture foundation. Second, we use the data-driven modelling and simulation method to achieve automated modelling. Third, we implement the system on the cloud using Java, MySQL, and the Anylogic platform, and verify the efficiency of the proposed method by experiments in the real workshop of a 3C (Computer, Communication, Consumer electronics) company. The experimental results show the proposed architecture can support the real-time resource allocation decisions to maximise the throughput in AFPLs. This paper makes contributions by proposing an architecture realising automatic modelling and data-driven simulation first in the cloud simulation environment, and filling the gap of dynamic resource allocation in the research of AFPLs.

In today’s customer-centric economy, the demand for personalized products has compelled corporations to develop manufacturing processes that are more flexible, efficient, and cost-effective. Flexible job shops offer organizations the agility and cost-efficiency that traditional manufacturing processes lack. However, the dynamics of modern manufacturing, including machine breakdown and new order arrivals, introduce unpredictability and complexity. This study investigates the multiplicity dynamic flexible job shop scheduling problem (MDFJSP) with new order arrivals. To address this problem, we incorporate the fluid model to propose a fluid randomized adaptive search (FRAS) algorithm, comprising a construction phase and a local search phase. Firstly, in the construction phase, a fluid construction heuristic with an online fluid dynamic tracking policy generates high-quality initial solutions. Secondly, in the local search phase, we employ an improved tabu search procedure to enhance search efficiency in the solution space, incorporating symmetry considerations. The results of the numerical experiments demonstrate the superior effectiveness of the FRAS algorithm in solving the MDFJSP when compared to other algorithms. Specifically, the proposed algorithm demonstrates a superior quality of solution relative to existing algorithms, with an average improvement of 29.90%; and exhibits an acceleration in solution speed, with an average increase of 1.95%.